1 /*
2 * Licensed to the Apache Software Foundation (ASF) under one or more
3 * contributor license agreements. See the NOTICE file distributed with
4 * this work for additional information regarding copyright ownership.
5 * The ASF licenses this file to You under the Apache License, Version 2.0
6 * (the "License"); you may not use this file except in compliance with
7 * the License. You may obtain a copy of the License at
8 *
9 * http://www.apache.org/licenses/LICENSE-2.0
10 *
11 * Unless required by applicable law or agreed to in writing, software
12 * distributed under the License is distributed on an "AS IS" BASIS,
13 * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
14 * See the License for the specific language governing permissions and
15 * limitations under the License.
16 */
17 package org.apache.commons.configuration2.io;
18
19 import java.io.File;
20 import java.net.URL;
21 import java.nio.ByteBuffer;
22 import java.nio.charset.Charset;
23 import java.nio.charset.StandardCharsets;
24
25 /**
26 * This class is a subset of org.apache.commons.io.FileUtils, git-svn-id:
27 * https://svn.apache.org/repos/asf/commons/proper/io/trunk@1423916 13f79535-47bb-0310-9956-ffa450edef68. The subset is
28 * determined by {@link FileLocatorUtils}. The copied constants and methods are <em>literally</em> copied.<br />
29 *
30 * See CONFIGURATION-521 for a discussion.
31 */
32 final class FileUtils {
33 /**
34 * The UTF-8 character set, used to decode octets in URLs.
35 */
36 private static final Charset UTF8 = StandardCharsets.UTF_8;
37
38 /**
39 * Convert from a {@code URL} to a {@code File}.
40 * <p>
41 * From version 1.1 this method will decode the URL. Syntax such as {@code file:///my%20docs/file.txt} will be correctly
42 * decoded to {@code /my docs/file.txt}. Starting with version 1.5, this method uses UTF-8 to decode percent-encoded
43 * octets to characters. Additionally, malformed percent-encoded octets are handled leniently by passing them through
44 * literally.
45 *
46 * @param url the file URL to convert, {@code null} returns {@code null}
47 * @return the equivalent {@code File} object, or {@code null} if the URL's protocol is not {@code file}
48 */
49 public static File toFile(final URL url) {
50 if (url == null || !"file".equalsIgnoreCase(url.getProtocol())) {
51 return null;
52 }
53 String fileName = url.getFile().replace('/', File.separatorChar);
54 fileName = decodeUrl(fileName);
55 return new File(fileName);
56 }
57
58 /**
59 * Decodes the specified URL as per RFC 3986, i.e. transforms percent-encoded octets to characters by decoding with the
60 * UTF-8 character set. This function is primarily intended for usage with {@link java.net.URL} which unfortunately does
61 * not enforce proper URLs. As such, this method will leniently accept invalid characters or malformed percent-encoded
62 * octets and simply pass them literally through to the result string. Except for rare edge cases, this will make
63 * unencoded URLs pass through unaltered.
64 *
65 * @param url The URL to decode, may be {@code null}.
66 * @return The decoded URL or {@code null} if the input was {@code null}.
67 */
68 static String decodeUrl(final String url) {
69 String decoded = url;
70 if (url != null && url.indexOf('%') >= 0) {
71 final int n = url.length();
72 final StringBuilder buffer = new StringBuilder();
73 final ByteBuffer bytes = ByteBuffer.allocate(n);
74 for (int i = 0; i < n;) {
75 if (url.charAt(i) == '%') {
76 try {
77 do {
78 final byte octet = (byte) Integer.parseInt(url.substring(i + 1, i + 3), 16);
79 bytes.put(octet);
80 i += 3;
81 } while (i < n && url.charAt(i) == '%');
82 continue;
83 } catch (final RuntimeException ignored) {
84 // malformed percent-encoded octet, fall through and
85 // append characters literally
86 } finally {
87 if (bytes.position() > 0) {
88 bytes.flip();
89 buffer.append(UTF8.decode(bytes));
90 bytes.clear();
91 }
92 }
93 }
94 buffer.append(url.charAt(i++));
95 }
96 decoded = buffer.toString();
97 }
98 return decoded;
99 }
100
101 }